host: phase2 daemon + health + auto-recovery (restore, recover, double-fork)

tests/test_host.py

@@ -297,6 +297,82 @@ class ServerRestartTest(unittest.TestCase):
                     pass
 
 
+class HealthRestoreRecoverTest(unittest.TestCase):
+    class FakeServer:
+        def initialize(self):
+            return {}
+
+        def list_threads(self):
+            return {"data": []}
+
+        def close(self):
+            pass
+
+    def test_corrupt_state_detected_and_restored_from_bak(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            path = os.path.join(tmp, "host-state.json")
+            good = {"tasks": {"a": {"status": "completed"}},
+                    "automations": [], "version": 3}
+            with open(path + ".bak", "w") as f:
+                json.dump(good, f)
+            with open(path, "w") as f:
+                f.write("{not json!!!")
+            strict, err = host.load_state_strict(path)
+            self.assertIsNone(strict)
+            self.assertIsNotNone(err)
+            ok, msg = host.restore_state(path)
+            self.assertTrue(ok, msg)
+            with open(path) as f:
+                restored = json.load(f)
+            self.assertEqual(restored["version"], 3)
+            self.assertTrue(os.path.exists(path + ".corrupt.") or
+                            any(fn.startswith("host-state.json.corrupt.")
+                                for fn in os.listdir(tmp)))
+
+    def test_restore_without_backup_fails_without_overwriting(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            path = os.path.join(tmp, "host-state.json")
+            with open(path, "w") as f:
+                f.write("{bad")
+            ok, msg = host.restore_state(path)
+            self.assertFalse(ok)
+            # 坏文件被改名留底，主文件已不在（不是被空 state 覆盖）
+            self.assertFalse(os.path.exists(path))
+
+    def test_recover_marks_old_running_only(self):
+        import time as _time
+        now = _time.time()
+        state = {"tasks": {
+            "old": {"status": "running", "created_at": now - 7200,
+                    "last_turn_at": now - 7200},
+            "fresh": {"status": "running", "created_at": now - 60,
+                      "last_turn_at": now - 60},
+            "done": {"status": "completed", "created_at": now - 7200},
+        }, "automations": []}
+        with tempfile.TemporaryDirectory() as tmp:
+            path = os.path.join(tmp, "host-state.json")
+            recovered = host.recover_interrupted(state, path,
+                                                 older_than=3600, cfg={})
+            self.assertEqual(recovered, ["old"])
+            self.assertEqual(state["tasks"]["old"]["status"], "interrupted")
+            self.assertEqual(state["tasks"]["fresh"]["status"], "running")
+
+    def test_health_with_fake_server(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            path = os.path.join(tmp, "host-state.json")
+            with open(path, "w") as f:
+                json.dump({"tasks": {}, "automations": [], "version": 1}, f)
+            with open(path + ".bak", "w") as f:
+                json.dump({"tasks": {}, "automations": [], "version": 1}, f)
+            report = host.run_health_check(
+                path, {}, "/bin/true", tmp, "deny",
+                server_factory=lambda: self.FakeServer())
+            self.assertTrue(report["ok"], report)
+            self.assertTrue(report["checks"]["state_valid"])
+            self.assertTrue(report["checks"]["backup_exists"])
+            self.assertTrue(report["checks"]["server_ok"])
+
+
 if __name__ == "__main__":
     unittest.main()